Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 471
    Prev
    Next
    INDEX
    Explanations

    technical and programming terms related to functionality

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "function" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cott
    -0.87
    pee
    -0.70
    creen
    -0.68
    yu
    -0.65
     Hemp
    -0.65
     Jed
    -0.64
    bows
    -0.63
    lake
    -0.63
    chu
    -0.62
     Lank
    -0.62
    POSITIVE LOGITS
    ality
    1.14
    ional
    1.04
    alities
    0.95
    aries
    0.94
    ative
    0.93
    ivity
    0.84
    ioned
    0.84
    inic
    0.83
    icular
    0.81
    istry
    0.80
    Activations Density 0.037%

    No Known Activations